Abstract

We propose a general framework for Object Recognition into regions and objects. In this framework, the
detection and recognition of objects proceed simultaneously with image segmentation in a competitive and
cooperative manner. Object detection is performed to check existence of objects in video and to precisely
locate that object. Object tracking is performed using monitoring objects spatial and temporal changes
during a video sequence, including its presence, position, size, shape, etc. A common approach for object
detection is to use information in a single frame. The tracking method requires an object detection
mechanism either in every frame or when the object first appears in the video.